Instructions to use IPEC-COMMUNITY/spatialvla-4b-224-pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IPEC-COMMUNITY/spatialvla-4b-224-pt with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="IPEC-COMMUNITY/spatialvla-4b-224-pt", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("IPEC-COMMUNITY/spatialvla-4b-224-pt", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IPEC-COMMUNITY/spatialvla-4b-224-pt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IPEC-COMMUNITY/spatialvla-4b-224-pt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IPEC-COMMUNITY/spatialvla-4b-224-pt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/IPEC-COMMUNITY/spatialvla-4b-224-pt

SGLang

How to use IPEC-COMMUNITY/spatialvla-4b-224-pt with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "IPEC-COMMUNITY/spatialvla-4b-224-pt" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IPEC-COMMUNITY/spatialvla-4b-224-pt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "IPEC-COMMUNITY/spatialvla-4b-224-pt" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IPEC-COMMUNITY/spatialvla-4b-224-pt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use IPEC-COMMUNITY/spatialvla-4b-224-pt with Docker Model Runner:
```
docker model run hf.co/IPEC-COMMUNITY/spatialvla-4b-224-pt
```

delinqu commited on Mar 16, 2025

Commit

886c455

verified ·

1 Parent(s): ca972dc

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

test_huggingface.py +1 -1

test_huggingface.py CHANGED Viewed

@@ -19,7 +19,7 @@ if __name__ == "__main__":
     image = Image.open("example.png").convert("RGB")
     images = [image] * args.num_images
-    prompt = "What action should the robot take to pick the cpu?"
     inputs = processor(images=images, text=prompt, unnorm_key="bridge_orig/1.0.0", return_tensors="pt")
     print(inputs)

     image = Image.open("example.png").convert("RGB")
     images = [image] * args.num_images
+    prompt = "What action should the robot take to pick the cup?"
     inputs = processor(images=images, text=prompt, unnorm_key="bridge_orig/1.0.0", return_tensors="pt")
     print(inputs)